List your company

Mathematical Reasoning on Average Across Seven Benchmarks (pass@k)

35.7Pass@1PASS
14.06819.68425.330.916Jun 28, 2026

Evaluation results

MethodLinks
PASS2026.0635.755
GRPO(ORM)2026.0629.853.1
Base Model (Qwen2.5-Math-7B)Backbone=Qwen2.5-Math-7B2026.0614.944.7